© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58373
    Prev
    Next
    INDEX
    Explanations

    competition, autonomy, dogma, breeds, injecting, bordering

    np_acts-logits-general · gemini-2.5-flash-lite

    prepositional phrases, particularly those with "of", "for", or "on" that form idiomatic expressions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prawie
    -1.70
     niveaux
    -1.69
     yzf
    -1.66
     ſont
    -1.66
     gsx
    -1.65
     ovp
    -1.65
     jetta
    -1.64
     tiroirs
    -1.64
    SUNG
    -1.62
     iveco
    -1.62
    POSITIVE LOGITS
     at
    2.33
     by
    1.78
     in
    1.70
     on
    1.53
     so
    1.49
     because
    1.48
     through
    1.48
     your
    1.44
    *}
    1.43
    expiresIn
    1.43
    Activations Density 0.098%

    No Known Activations